Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnly/destructive annotations, it discloses non-obvious behavior: summarized_kinds omits large kinds, members_complete flips false, count may exceed members length, and the resolved members are always a live lens rather than a pinned list. This is exactly the kind of behavioral nuance an agent must know before trusting the returned member count.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but every sentence earns its place; it front-loads the core concept and then layers edge cases (summarized kinds, count mismatch) without digression. Slightly verbose relative to a two-line alternative, but the complexity of the behavior justifies the length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a rich output schema, 100% parameter coverage, and annotations for safety, this description fully covers what the agent needs: return shape, member set semantics, draft-preview behavior, summarized-kind caveats, and what to call instead for full enumeration. Nothing material is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents slug, app_id, and version. The description adds value by clarifying version semantics (published vs latest draft, omit 0 for current), but it doesn't add much beyond the schema's version description. Baseline 3 is appropriate because structured coverage is complete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb ('Resolve') and resource ('an app's LIVE member set'), then defines exactly what that set is: the concrete resources its selector currently matches, resolved as union(prefixes) + includes − excludes. This clearly distinguishes it from generic getters like get_app or get_app_version.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use it ('Use this to see or verify what an app contains'), how version selection behaves ('pass version to preview a draft's members before publishing'), and when NOT to use it for collection items ('see that kind's own list tool with one of the reported slug_prefix values... e.g. list_datafiles'). It names the alternative tool and never claims to page whole collections.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.